© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 5277
    Prev
    Next
    INDEX
    Explanations

    contrast

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Usually
    -0.78
     Usually
    -0.74
     usually
    -0.73
     suele
    -0.68
     huwa
    -0.68
    usually
    -0.66
     gewöhnlich
    -0.66
     genellikle
    -0.64
     généralement
    -0.63
    Typically
    -0.63
    POSITIVE LOGITS
    Sklici
    0.61
     in
    0.58
    !";
    0.56
     conceivably
    0.55
    !]
    0.54
    !!</
    0.54
    ệt
    0.53
    iosamente
    0.52
     
    0.52
    !</
    0.50
    Activations Density 0.049%

    No Known Activations